/search-gemini
Web search via Gemini CLI for latest information. Trigger with "search the web", "look up latest info", "search with Gemini".
$ npx -y skills add wasabeef/claude-code-cookbook --skill search-gemini --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/search-gemini
Context preview
The summary Claude sees to decide when to auto-load this skill.
Web search via Gemini CLI for latest information. Trigger with "search the web", "look up latest info", "search with Gemini".
SKILL.md
search-gemini.SKILL.mddescription: 'Web search via Gemini CLI for latest information. Trigger with "search the web", "look up latest info", "search with Gemini".'
allowed-tools:
- Bash(gemini *)
Web search via Gemini CLI for latest information
Execute web searches via Gemini CLI to obtain the latest information.
Usage
# Web search via Gemini CLI (required)
gemini --prompt "WebSearch: <search_query>"
Basic Examples
# Using Gemini CLI
gemini --prompt "WebSearch: React 19 new features"
gemini --prompt "WebSearch: TypeError Cannot read property of undefined solution"
Collaboration with Claude
# Document search and summarization
gemini --prompt "WebSearch: Next.js 14 App Router official documentation"
"Summarize the search results and explain the main features"
# Error investigation
cat error.log
gemini --prompt "WebSearch: [error_message] solution"
"Propose the most appropriate solution from the search results"
# Technology comparison
gemini --prompt "WebSearch: Rust vs Go performance benchmark 2026"
"Summarize the performance differences from the search results"
Detailed Examples
# Information gathering from multiple sources
gemini --prompt "WebSearch: GraphQL best practices 2026 multiple sources"
"Summarize information from multiple reliable sources in the search results"
# Investigating changes over time
gemini --prompt "WebSearch: JavaScript ES2015 ES2016 ES2017 ES2018 ES2019 ES2020 ES2021 ES2022 ES2023 ES2024 features"
"Summarize the main changes in each version in chronological order"
# Search limited to specific domain
gemini --prompt "WebSearch: site:github.com Rust WebAssembly projects stars:>1000"
"List the top 10 projects by number of stars"
# Latest security information
gemini --prompt "WebSearch: CVE-2024 Node.js vulnerabilities"
"Summarize the impact and countermeasures of found vulnerabilities"
Prohibited Items
- **Prohibited to use Claude's built-in WebSearch tool**
- When web search is needed, always use `gemini --prompt "WebSearch: ..."`
Important Notes
- **When Gemini CLI is available, always use `gemini --prompt "WebSearch: ..."`**
- Web search results are not always the latest
- It is recommended to verify important information with official documentation or reliable sources
Read more
description: 'Web search via Gemini CLI for latest information. Trigger with "search the web", "look up latest info", "search with Gemini".' allowed-tools: - Bash(gemini *)
Web search via Gemini CLI for latest information
Execute web searches via Gemini CLI to obtain the latest information.
Usage
# Web search via Gemini CLI (required) gemini --prompt "WebSearch: <search_query>"
Basic Examples
# Using Gemini CLI gemini --prompt "WebSearch: React 19 new features" gemini --prompt "WebSearch: TypeError Cannot read property of undefined solution"
Collaboration with Claude
# Document search and summarization gemini --prompt "WebSearch: Next.js 14 App Router official documentation" "Summarize the search results and explain the main features" # Error investigation cat error.log gemini --prompt "WebSearch: [error_message] solution" "Propose the most appropriate solution from the search results" # Technology comparison gemini --prompt "WebSearch: Rust vs Go performance benchmark 2026" "Summarize the performance differences from the search results"
Detailed Examples
# Information gathering from multiple sources gemini --prompt "WebSearch: GraphQL best practices 2026 multiple sources" "Summarize information from multiple reliable sources in the search results" # Investigating changes over time gemini --prompt "WebSearch: JavaScript ES2015 ES2016 ES2017 ES2018 ES2019 ES2020 ES2021 ES2022 ES2023 ES2024 features" "Summarize the main changes in each version in chronological order" # Search limited to specific domain gemini --prompt "WebSearch: site:github.com Rust WebAssembly projects stars:>1000" "List the top 10 projects by number of stars" # Latest security information gemini --prompt "WebSearch: CVE-2024 Node.js vulnerabilities" "Summarize the impact and countermeasures of found vulnerabilities"
Prohibited Items
- **Prohibited to use Claude's built-in WebSearch tool**
- When web search is needed, always use `gemini --prompt "WebSearch: ..."`
Important Notes
- **When Gemini CLI is available, always use `gemini --prompt "WebSearch: ..."`**
- Web search results are not always the latest
- It is recommended to verify important information with official documentation or reliable sources
A collection of commands, roles, and automation scripts for Claude Code. Automate your workflow without unnecessary confirmations, allowing you to focus on what matters.
Repo: wasabeef/claude-code-cookbook
Other skills on claude-code-cookbook.
- /analyze-dependencies
Analyze project dependencies and evaluate architectural health. Trigger with "analyze dependencies", "detect circular dependencies", "architecture issues?", "check module coupling", "find layer violations". Generates dependency matrix, fan-in/fan-out analysis, and prioritized
Open skill - /analyze-performance
Performance analysis based on Core Web Vitals with UX scoring. Trigger with "analyze performance", "improve speed", "check Core Web Vitals", "page speed", "improve LCP", "identify performance issues".
Open skill - /check-fact
Verify information accuracy against codebase and documentation. Trigger with "is this correct?", "fact check", "verify this", "is this accurate?".
Open skill - /check-prompt
Evaluate and improve AI prompt quality. Trigger with "check this prompt", "evaluate prompt quality", "improve this prompt".
Open skill - /commit-message
Generate commit messages from staged changes. Trigger with "suggest commit message", "generate commit message", "what should the commit say?", "write commit message".
Open skill - /context7
Search technical documentation via Context7 MCP. Trigger with "check the docs", "look up documentation", "how to use this library?", "API reference".
Open skill

